© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12242
    Prev
    Next
    INDEX
    Explanations

    Democratic spending programs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags uncommon or irregular tokens—slang contractions, numeric or punctuation-heavy strings, and other out-of-vocabulary bits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    начала
    0.82
     físicos
    0.81
    最初に
    0.79
     появление
    0.78
    鄔
    0.77
    藉
    0.77
    Ꮷ
    0.77
    эй
    0.77
    กาย
    0.76
     elektrom
    0.76
    POSITIVE LOGITS
    ',
    0.75
     COMMIT
    0.72
    ')->
    0.70
    polit
    0.67
    👰
    0.64
    >):
    0.63
    ")->
    0.63
    ':
    0.62
    🎌
    0.62
    velope
    0.62
    Activations Density 0.000%

    No Known Activations